End to End Dialogue Transformer
This work addresses dialogue system development for applications like small talk or booking, but it is incremental as it primarily swaps RNNs with Transformers without major methodological breakthroughs.
The authors tackled the problem of building dialogue systems by proposing a Transformer-based architecture to replace the RNN-based Sequicity model, achieving results in an end-to-end sequence-to-sequence fashion.
Dialogue systems attempt to facilitate conversations between humans and computers, for purposes as diverse as small talk to booking a vacation. We are here inspired by the performance of the recurrent neural network-based model Sequicity, which when conducting a dialogue uses a sequence-to-sequence architecture to first produce a textual representation of what is going on in the dialogue, and in a further step use this along with database findings to produce a reply to the user. We here propose a dialogue system based on the Transformer architecture instead of Sequicity's RNN-based architecture, that works similarly in an end-to-end, sequence-to-sequence fashion.